README.md

---
language: en
license: mit
tags:
  - sentence-transformers
  - embeddings
  - bert
pipeline_tag: sentence-similarity
---

# bne-float-384

Float32 baseline for the **Binary Native Embeddings** project.

- Backbone: `prajjwal1/bert-mini` (4L × 256d, ~11M params)
- Output: 384-dim float32 via Linear(256→384) + mean pooling
- Training: MultipleNegativesRankingLoss on NLI 550k pairs, 3 epochs

| STS-B Spearman | Recall@10 (SciFact) | Memory / 1k vecs |
|---|---|---|
| 0.7355 | 0.3131 | 1.46 MB |

Part of [binary-native-embeddings-for-CPU-Retrieval](https://github.com/korben99/binary-native-embeddings-for-CPU-Retrieval) · [Discussion](https://discuss.huggingface.co/t/native-binary-embeddings-experiment-curious-about-your-thoughts/177107)

## Usage

```python
import torch
from transformers import BertTokenizer
from huggingface_hub import hf_hub_download
from models.float_embedder import FloatEmbedder

tokenizer = BertTokenizer.from_pretrained("prajjwal1/bert-mini")
model = FloatEmbedder(output_dim=384)
weights = hf_hub_download("korben99/bne-float-384", "float_embedder.pt")
model.load_state_dict(torch.load(weights, map_location="cpu"))
model.eval()

vecs = model.encode(["hello world"], tokenizer)  # (1, 384) float32
```